Lec 08. Architectures: Transformers

Name: Lec 08. Architectures: Transformers
Uploaded: 2026-02-11T14:39:28Z
Duration: 1 h 14 min 35 s
Description: This video introduces transformers, focusing on three key ideas: tokens, attention, and positional codes. It also explores how transformers relate to MLPs, GNNs, and CNNs as variations on common principles.

1:14:35

Up Next

Lec 09. Hacker's Guide to Deep Learning

Continue

This video introduces transformers, focusing on three key ideas: tokens, attention, and positional codes. It also explores how transformers relate to MLPs, GNNs, and CNNs as variations on common principles.